Aiming at the complex environment, unexpected situations, and multi-constraint problems faced by unmanned aerial vehicle (UAV) mission planning systems in dynamic scenes, an online task allocation method based on improved dynamic ant colony labor division (IDACLD) is proposed. The typical scene of multi-UAV task allocation is described, and a heterogeneous multi-UAV multi-constraint model is established via multigroup settings. According to this framework, the environmental stimulus and response thresholds of the dynamic ant colony division of labor model are redesigned, the coupling between task allocation and path planning is considered, and the RRT* algorithm is used to complete path cost estimation, which makes the task allocation result more reasonable in environments containing obstacles. Considering cases involving UAV faults, this study proposes different fault handling strategies to distinguish different fault types and better fit the actual situation of UAV missions. Simulation results demonstrate that the proposed method can quickly and effectively solve the task allocation problem of multiple UAVs in a dynamic environment.
With the advent of unmanned aerial vehicle (UAV) swarm technology, countering UAV swarms has emerged as a pressing challenge requiring immediate attention. Employing UAV swarms with high efficiency-to-cost ratios to counter, disrupt, and intercept enemy UAV swarms has been proven to be a relatively effective countermeasure, prompting extensive research in this field. To comprehensively analyze the progress of intelligent decision-making technology in UAV swarm confrontation, this study initially examined the primary technical challenges faced by intelligent decision-making technology, outlining the establishment and resolution of submodels as the central theme. The study presents three primary models, namely, mathematical programming, game theory, and Markov decision processes, and provides an overview of their current applications and challenges based on relevant theories. Subsequently, the study elaborates on the solution methods for each mathematical model and emphasizes the reinforcement learning-based solving algorithm, highlighting its advantages in the domain of adversarial intelligent decision making. Finally, we summarize the current state and limitations of UAV swarm intelligent decision-making research and offer a perspective on future trends in this field, thereby offering novel avenues for further research.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.